CN105632049B - A kind of early warning method and device based on wearable device - Google Patents
A kind of early warning method and device based on wearable device Download PDFInfo
- Publication number
- CN105632049B CN105632049B CN201410638409.6A CN201410638409A CN105632049B CN 105632049 B CN105632049 B CN 105632049B CN 201410638409 A CN201410638409 A CN 201410638409A CN 105632049 B CN105632049 B CN 105632049B
- Authority
- CN
- China
- Prior art keywords
- information
- wearable device
- target object
- wearer
- environmental
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/012—Head tracking input arrangements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/16—Actuation by interference with mechanical vibrations in air or other fluid
- G08B13/1654—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems
- G08B13/1672—Actuation by interference with mechanical vibrations in air or other fluid using passive vibration detection systems using sonic detecting means, e.g. a microphone operating in the audio frequency range
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Emergency Alarm Devices (AREA)
- Child & Adolescent Psychology (AREA)
- Alarm Systems (AREA)
- Computer Security & Cryptography (AREA)
- Automation & Control Theory (AREA)
- User Interface Of Digital Computer (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
Abstract
本申请公开了一种基于可穿戴设备的预警方法及相应的可穿戴设备。该预警方法的一具体实施方式包括：接收经由第一可穿戴设备获取的周围环境信息，环境信息包括环境图像信息和环境音频信息；基于环境信息，确定是否存在危险事件；以及响应于确定存在危险事件，提供警报信息。该预警方法为用户提供实时的危险检测与预警报告，提高了用户的安全系数。
The present application discloses an early warning method based on a wearable device and a corresponding wearable device. A specific embodiment of the early warning method includes: receiving surrounding environment information obtained via a first wearable device, the environment information includes environmental image information and environmental audio information; determining whether there is a dangerous event based on the environmental information; and in response to determining that there is a danger events, which provide alert information. The early warning method provides users with real-time danger detection and early warning reports, and improves the safety factor of users.
Description
Technical field
This application involves information technology fields, and in particular to field of terminal technology, more particularly to one kind are set based on wearable
Standby method for early warning and device.
Background technique
Known there are some wearable devices, such as head-mounted display, are able to detect dangerous objects, such as vehicle,
And it sends a warning message.In these schemes, the danger of vehicle is detected using picture signal.It is known that there are it is some can
Wearable device is detected the danger of vehicle using audio signal and provides alarm.
Summary of the invention
Above-mentioned hazard detection and early warning scheme have the following deficiencies: first, danger define it is excessively narrow, only comprising from
The danger of vehicle ignores the danger from extraneous biology；Second, the sensor used is excessively single, therefore to danger
Detect omission factor with higher and false alarm rate；Third does not have third party's assist in functions, then cannot perceive in equipment of itself
When dangerous, user is likely to just come to harm.
In view of this, in order to overcome said one or multiple defects, the application provides a kind of based on the pre- of wearable device
Alarm method, device and corresponding wearable device.
On the one hand, this application provides a kind of danger early warning methods, which comprises receives and wearable sets via first
The standby ambient condition information obtained, the environmental information includes ambient image information and environmental audio information；Based on the environment
Information, it is determined whether dangerous event；And in response to the dangerous event of determination, provide warning information.
In some embodiments, this method further includes receiving the information obtained via the second wearable device, the letter
Breath includes at least one of the following: the biological information of the wearer of second wearable device, environmental information and described second
The information that wearable device generates；And hazard event is determined whether there is also based on the institute obtained via the second wearable device
State information.
In some embodiments, the hazard event that determines whether there is includes: to be examined based on the ambient image information
It surveys the body characteristics of target object and determines that target object reaches the time of corresponding wearable device；Based on the environmental audio
The audio frequency characteristics of information extraction target object；And corresponding wear is reached according to body characteristics, the target object of target object
The time of equipment and the audio frequency characteristics of target object are worn, the danger classes of target object is assessed.
In some embodiments, the target object is vehicle, and the audio frequency characteristics of the target object include vehicle
Whistle frequency.
In some embodiments, the target object is animal, and the body characteristics of the target object include animal
At least one of in tooth, tail and eyes, the audio frequency characteristics of the target object include loudness, tone and Mel frequency cepstral
At least one of in coefficient MFCC.
In some embodiments, the target object is behaved, and the body characteristics of the target object include face, body
At least one of dry, four limbs, the audio frequency characteristics of the target object include human speech, the regular cepstrum coefficient of speech energy
PNCC。
In some embodiments, the danger classes of the assessment target object includes: the shape based on the target object
At least one of in body characteristics and audio frequency characteristics, identify whether the target object is stranger；If the target object is footpath between fields
Stranger is then executed at least one of following to determine fraud likelihood score: being analyzed the language of the target object based on fraud reference model
Sound content；Analyze the facial characteristics variation of the target object；And the behavior act variation of the analysis target object；And
The danger classes is determined based on the fraud likelihood score.
In some embodiments, the environmental information further includes Weather information and/or odiferous information, wherein described in obtaining
Weather information, which is included at least one of the following:, senses weather conditions via sensor；And weather forecast is received via network；And
It is described to determine whether there is hazard event further include: described danger etc. is adjusted based on the Weather information and/or odiferous information
Grade.
In some embodiments, the method also includes: receive via first wearable device obtain described in
The biological information of the wearer of first wearable device；It is and described to determine whether there is hazard event further include: based on described
Biological information adjusts the danger classes.
In some embodiments, the offer warning information includes: the wearer for obtaining first wearable device
Feedback information；And the warning information is provided to the wearer based on the feedback information.
In some embodiments, the offer warning information includes: to provide corresponding grade based on the danger classes
Warning information.
In some embodiments, the method also includes: receive via first wearable device obtain described in
The biological information of the wearer of first wearable device；And the offer warning information include: based on the biological information come
Adjustment provides the mode of warning information.
Second aspect, this application provides a kind of risk early warning devices.The device includes: receiving unit, is configured to connect
The ambient condition information obtained via the first wearable device is received, the environmental information includes ambient image information and environmental audio
Information；Hazard event determination unit is configured to based on the environmental information, it is determined whether dangerous event；And alarm
Information provider unit is configured to provide warning information in response to the dangerous event of determination.
It should be noted that the corresponding embodiment of first aspect also can be applied to second aspect.
The third aspect, this application provides a kind of wearable device, the wearable device includes: environment information acquisition list
Member, the environmental information being configured to around obtaining, including the imaging sensor for obtaining ambient image information and for obtaining
The audio sensor of environmental audio information；Processing unit is configured to based on the environmental information, it is determined whether dangerous thing
Part, and for providing warning information in response to the dangerous event of determination；And alarm unit, it is configured to according to
Warning information is alarmed.
In some embodiments, wearable device can also include transmission unit, and being configured to reception can from second
The information of wearable device, the information include at least one of the following: the biological information of the wearer of second wearable device,
The information that environmental information and second wearable device generate.In this embodiment, processing unit can further match
It sets for also determining whether there is hazard event based on the information from the second wearable device.
In some embodiments, the processing unit can further be configured to determine whether there is as got off
Hazard event: body characteristics based on the ambient image information detected target object and determine target object reach it is corresponding can
The time of wearable device；Audio frequency characteristics based on the environmental audio information extraction target object；And according to target object
Body characteristics, target object reach the time of corresponding wearable device and the audio frequency characteristics of target object, assess target pair
The danger classes of elephant.
In some embodiments, the target object is vehicle, and the audio frequency characteristics of the target object include vehicle
Whistle frequency.
In some embodiments, the target object is animal, and the body characteristics of the target object include animal
At least one of in tooth, tail and eyes, the audio frequency characteristics of the target object include loudness, tone and Mel frequency cepstral
At least one of in coefficient MFCC.
In some embodiments, the target object is behaved, and the body characteristics of the target object include face, body
At least one of dry, four limbs, the audio frequency characteristics of the target object include human speech, the regular cepstrum coefficient of speech energy
PNCC。
In some embodiments, the processing unit can further be configured to be based on such as getting off to assess target object
Danger classes: in body characteristics and audio frequency characteristics based on the target object at least one of, identify the target object
It whether is stranger；If the target object is stranger, executes and at least one of following cheat likelihood score to determine: based on taking advantage of
Swindleness reference model analyzes the voice content of the target object；Analyze the facial characteristics variation of the target object；And analysis
The behavior act of the target object changes；And the danger classes is determined based on the fraud likelihood score.
In some embodiments, the environmental information further includes Weather information and/or odiferous information, wherein environmental information
Acquisition unit can also include: humidity sensor, for sensing weather conditions；And/or smell sensor, for sensing surrounding ring
The smell in border.Wearable device can also include network communication unit, for receiving weather forecast via network.Embodiment party herein
In formula, processing unit can also be configured to: the danger classes is adjusted based on the Weather information and/or odiferous information.
In some embodiments, which can also include: biometric information sensor, for obtain it is described can
The biological information of the wearer of wearable device；And the processing unit can also be configured to: based on the biological information come
Adjust the danger classes.
In some embodiments, the processing unit can further be configured to obtain wearing for the wearable device
The feedback information of wearer；And the warning information is provided based on the feedback information.
In some embodiments, the processing unit can be further configured to based on danger classes offer pair
Answer the warning information of grade.
In some embodiments, the wearable device can also include: biometric information sensor, described for obtaining
The biological information of the wearer of wearable device；And the processing unit can further configure based on the biological information come
Adjustment provides the mode of warning information.
Method for early warning based on wearable device, device and corresponding wearable device provided by the present application, by that can wear
The environment information acquisition unit for wearing equipment obtains the environmental information of surrounding, and environmental information may include different types of information, example
Include such as ambient image information and environmental audio information, is then based on these environmental informations, it is determined whether dangerous event.Such as
Fruit determines dangerous event, then provides a user warning information.This method by multiple sensors provide a user comprehensively and
When danger early warning, improve the safety coefficient of user.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows the exemplary block diagram of the danger early warning system provided by the present application based on wearable device；
The process of the one embodiment for the danger early warning method based on wearable device that Fig. 2 shows provided by the present application
Figure；
Fig. 3 shows the flow chart of an exemplary realization of the method and step 202 of Fig. 2；
Fig. 4 shows the flow chart of an exemplary realization of the method and step 303 of Fig. 3；
Fig. 5 shows the structural frames of one embodiment of the risk early warning device provided by the present application based on wearable device
Figure；
Fig. 6 shows a kind of structural block diagram of exemplary realization of the threat level assessment subelement 523 in Fig. 5；And
Fig. 7 shows an exemplary scene of the danger early warning method provided by the present application based on wearable device.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Referring to FIG. 1, the exemplary knot of it illustrates the provided by the present application danger early warning system based on wearable device
Structure block diagram.
As shown in Figure 1, the danger early warning system mainly includes wearable device 100 comprising environment information acquisition unit
110, processing unit 120 and alarm unit 130.
Environment information acquisition unit 110 may include multiple sensors, for sensing different types of environmental information.Generally
For, environment information acquisition unit 110 includes imaging sensor 111 and audio sensor 112.
Imaging sensor or photosensitive element are a kind of equipment that optical imagery is converted into electronic signal.In this implementation
In example, imaging sensor 111 can be used for obtaining the real-time image information in ambient enviroment.Real-time image information may include week
Any information of user security may be jeopardized in collarette border.For example, real-time image information can include but is not limited to pavement behavior,
Traveling state of vehicle, neighbouring biology, including personnel and animal etc..
Audio sensor may include sound pick-up or sound pick-up array.In the present embodiment, audio sensor 112 can be used
Real-time audio information in acquisition ambient enviroment.Real-time audio information may include that may jeopardize user security in ambient enviroment
Any information.For example, real-time audio information can include but is not limited to vehicle whistle, thunder, people's sound of speaking, animal cry
Deng.
Other than the sensor, additionally, environment information acquisition unit 110 can also include other kinds of sensing
Device.For example, environment information acquisition unit 110 can also include humidity sensor 113, smell sensor 114, velocity sensor
(not shown), atmosphere pressure sensor (not shown) etc..Humidity sensor 113 can be used for sensing the humidity of ambient enviroment, with
In for example determining weather conditions.Smell sensor 114 for example can be used for detecting certain a kind of or a few class smell in ambient enviroment
Or gas, these gases for example can be the gas for jeopardizing the element of user security comprising hazardous chemical etc., such as an oxidation
Carbon or smog.Velocity sensor for example can be used for sensing the speed of the wearer 10 of the wearable device 100.Atmospheric pressure sensing
Device for example can be used for sensing the atmospheric pressure of ambient enviroment, for for example determining weather conditions.Those skilled in the art can be with
Understand, environment information acquisition unit 110 can also include currently known and exploitation in the future any kind of for sensing week
Enclose the sensor of environmental aspect.Optionally, wearable device 100 can also include network communication unit 150, may be coupled to
Such as internet 20, with from network acquisition information.For example, weather forecast can be received from network by network communication unit 150,
To obtain the Weather information of ambient enviroment.
Optionally, other than environment information acquisition unit 110, wearable device 100 can also include that biological information passes
Sensor 160.Biometric information sensor 160 is sensitive to biological substance and its material concentration is converted to what electric signal detected
Instrument.In the present embodiment, biometric information sensor 160 can be used for sensing wearable device 100 wearer 10 (that is,
User) biological information.The biological information of user may include the information of the various physiological status that can characterize user.For example,
Biological information can include but is not limited to heart rate, blood pressure, body temperature, respiratory rate etc..
Processing unit 120 in wearable device 100 according to various information acquired in wearable device for determining
With the presence or absence of hazard event, and for providing warning information in response to the dangerous event of determination.Processing unit 120 is for example
May be configured to: analysis ambient image information analyzes environmental audio information, and assesses danger etc. based on above-mentioned analysis
Grade.
Processing unit 120 may be configured to analysis ambient image information, to be possible to jeopardize user's peace from wherein acquisition
Full information.For example, processing unit 120 can be examined based on the ambient image information that environment information acquisition unit 110 is transmitted
Survey the body characteristics of target object.Target object for example can be vehicle, animal, people etc..Vehicle can include but is not limited to card
Vehicle, kart, motorcycle etc..When target object is animal (such as vagrant dog, strong dog etc.), body characteristics for example may be used
To include but is not limited to the tooth, tail, eyes etc. of animal.When target object is people, body characteristics for example may include
But be not limited to face, trunk and four limbs etc..If target object is movement, processing unit 120 can also determine target object
The time of the wearable device is reached, namely reaches the time of wearer.
Processing unit 120 can also be configured to analysis environmental audio information, to be possible to jeopardize user from wherein acquisition
The information of safety.For example, processing unit 120 can based on the environmental audio information that environment information acquisition unit 110 is transmitted come
Extract the audio frequency characteristics of target object.Similarly, target object includes but is not limited to vehicle, animal, people etc..When target object is
When vehicle, audio frequency characteristics for example can include but is not limited to whistle frequency of vehicle etc..When target object is animal, sound
Frequency feature for example can include but is not limited to loudness, tone and Mel frequency cepstral coefficient MFCC etc..When target object is people,
Its audio frequency characteristics for example can include but is not limited to regular cepstrum coefficient PNCC of human speech, speech energy etc..
Processing unit 120 can also be configured to assess the danger etc. of target object based on above-mentioned image and audio analysis
Grade.For example, processing unit 120 can reach corresponding wearable device according to body characteristics, the target object of target object
The audio frequency characteristics of time and target object assess the danger classes of target object.When target object is people, processing unit
120 can cheat assessment with further progress stranger.The specific implementation for cheating assessment about stranger is described further below.
Optionally, processing unit 120 can also be configured to adjust assessed danger etc. based on various additive factors
Grade.In one implementation, processing unit 120 can be based on the sensed Weather information of environment information acquisition unit 110 and/or gas
Taste information adjusts danger classes.For example, when for rain and snow weather, it is contemplated that road surface slippery situation, vehicle be easy road surface slide and
Unexpected danger is generated, therefore danger classes can correspondingly be turned up.In another example when detecting toxic gas, it can also
Danger classes is turned up.In another implementation, processing unit 120 can be sensed based on biometric information sensor 160
User physiology situation information adjusts danger classes.For example, when sense user's physiological status it is bad when, such as heart rate it is too fast,
Hyperpiesia is short of breath, and danger classes can correspondingly be turned up.
Processing unit 120 is also configured to provide warning information in response to the dangerous event of determination.In some embodiment party
In formula, processing unit 120 is further configured to obtain the feedback information of the wearer of wearable device, and is based on feedback letter
Breath provides warning information.In this embodiment, danger early warning system may include user preference database (not shown), wherein
It is stored with user preference data, such as response data or feedback data to various danger early warnings.Processing unit 120 can pass through
User preference database is retrieved to provide the warning information presented in such a way that user likes or is suitble to.
Alarm unit 130 is configured to be alarmed according to the warning information that processing unit 120 provides.Alarm unit 130
It may include various user interaction devices, for example, loudspeaker, display, vibrator etc., in order to provide different type of alarms.
Type of alarm can depending on user preferences, including but not limited to visually, audible or mode can be touched, such as by image, text,
The modes such as sound or vibration, there is no limit in this regard by the application.
In some embodiments, wearable device 100 may include third party's assist in functions.For example, wearable device
100 can also include transmission unit 140.Transmission unit 140 may be configured to receive from other wearable devices (such as with
The wearable device at family 40) information.Such information can include but is not limited to the biology letter of the wearer of wearable device
The information that breath, environmental information and wearable device generate, such as the processing unit danger classes generated of wearable device
Information.Further, processing unit 120 can be based further on the information from other wearable devices to determine whether there is
Hazard event.It by information sharing mode, can be provided for user from third-party early warning, to increase safe system
Number.
In one implementation, danger early warning system may include shared data bank 30.Wearable device can be by their own
Information upload in shared data bank 30, to be shared with other equipment.In this implementation, each wearable device can be by altogether
Database 30 is enjoyed to receive the information of other wearable devices offer.
In another implementation, connection can directly be established between wearable device to transmit information.For example, adult's can
Wearable device and the wearable device of child can be matched to establish and be directly connected to, to can be total between two wearable devices
Enjoy information.
The wearable device 100 of the application can include but is not limited to headset equipment, Wrist belt-type equipment, Intelligent bracelet,
Smartwatch etc..Those skilled in the art can according to need to be designed to wearable device 100 be suitable for dressing and be suitble to
Any equipment of sensing work is carried out in the various sensors of wearable device, there is no limit in this regard by the application.
The method for early warning based on wearable device of the application is described below with reference to flow chart.
The process of the one embodiment for the danger early warning method based on wearable device that Fig. 2 shows provided by the present application
Figure.In the following description, the wearable device for using " the first wearable device " Lai Zhidai to be currently discussed, " second can for use
Wearable device " refers to other in addition to the wearable device being currently discussed wearable devices with similar functions.It should
Understanding, the use of " first " and " second ", which is not intended to, is defined wearable device itself, and only to facilitate difference is retouched
It states.
As shown in Fig. 2, in step 201, receiving the ambient condition information obtained via the first wearable device, environment letter
Breath includes ambient image information and environmental audio information.
When user is in some environment, such as walk on road, when being in indoor environment, may have it is some potential
Danger, for example, there are the danger of toxic gas and footpaths between fields in the danger of driving vehicle, the danger of surrounding animal, air
The danger of the potential fraud of stranger.In the present embodiment, the environment around the wearable device that user wears is available
Information, to detect possible potential danger.In general, environmental information includes image information and audio letter in ambient enviroment
Breath.For example, user walks when on road, image information may include the vehicle of periphery traveling, can also include near user
People and the/information such as animal and its behavior state.It can also include the direction of motion, the movement velocity etc. of object in multiple image information
Information.Imaging sensor 111 shown in FIG. 1 can be used to sense in image information.Audio-frequency information may include surrounding vehicles
It blows a whistle frequency, can also include the information such as cry of the voice of people near user, animal.Fig. 1 can be used in audio-frequency information
Shown in audio sensor 112 sense.
Then, in step 202, based on acquired environmental information, it is determined whether dangerous event.
In the present embodiment, it is based on environmental information, it is determined whether dangerous event refers to the image according at least to acquisition
And audio-frequency information, judge the dangerous situation of ambient enviroment, provides corresponding danger classes.For example, judging vehicle according to image information
Driving direction is also to be directed towards user away from user, judges whether vehicle injures the safety of user at a distance from user, also
Including judging whether the animal near user is in angry state according to audio-frequency information, there is the possibility etc. of harm users.Hereafter will
It is described in detail how to determine whether there is hazard event in conjunction with Fig. 3.
Finally, in step 203, in response to the dangerous event of determination, providing warning information.
In the present embodiment, however, it is determined that dangerous event then provides a user warning information, to remind user to leave this
Ground or change direction of travel etc..In some embodiments, warning information can be depending on scene and/or user preferences.It can wear
Wearing equipment can be by the feedback information of user, such as to the response data or feedback data of various danger early warnings, sends user to
Preference database is saved standby use later.However, wearable device can be from the user preference for being stored with user preference
Database obtains the feedback information of user, and corresponding warning information is provided based on these feedback informations.For example, type of alarm
It can include but is not limited to vision, the sense of hearing and tactile manner.The content of alarm may include image, text, sound or combinations thereof
Deng.
In a further embodiment, the warning information of corresponding grade is also provided based on identified danger classes.Example
Such as, when danger classes is lower, it can provide that volume is lower, the lower alarm of frequency；It, can be with and when danger classes is higher
There is provided that volume is higher, the higher alarm of frequency.Alternatively, a variety of type of alarms can also be taken same when danger classes is higher
When use, such as not only issue alarm, but also provide vibration to remind user.
It is also based on the biological information of the wearer of wearable device in yet other embodiments, to adjust offer alarm
The mode of information.The biological information of user can react the physiological status and/or the state of mind of user.Different physiological status
And/or the state of mind has different reaction and processing to dangerous arrival.Correspondingly, wearable device can be used for this
Family provides different type of alarms.For example, at this moment treating dangerous reaction can be slower when the state of mind of user is poor
It is blunt, or be easier to ignore to fall danger.In order to avoid the type of alarm by possible injury, wearable device can be quicker
Sense, for example, alarm volume is higher, frequency faster, etc..
The danger early warning method provided by the above embodiment of the application is believed by the environment that wearable device obtains surrounding
Breath, environmental information may include different types of information, such as ambient image information and environmental audio information.Wearable device base
In these environmental informations, it is determined whether dangerous event, if it is determined that dangerous event then provides a user alarm signal
Breath.This method provides a user comprehensively timely danger early warning by multiple sensors, improves the safety coefficient of user.Separately
Outside, not only include vehicle to dangerous detection, can also include extraneous biology, such as animal and people.
With further reference to Fig. 3, it illustrates the flow charts of an exemplary realization of the method and step 202 of Fig. 2, namely show
A kind of example implementation of hazard event is gone out how to determine whether there is.
As shown in figure 3, in step 301, analyzing ambient image information to be possible to jeopardize user security from wherein acquisition
Information.Ambient image information both may include wearable device itself captured image, also may include that other wearable set
Standby captured image.For example, when two wearable devices carry out that data can be transmitted between each other, data can wrap with clock synchronization
The information that respective captured image information, audio-frequency information and respective wearable device generate is included but be not limited to, such as is determined
Danger classes, etc..
In this embodiment, analysis ambient image information may include the body characteristics of detected target object.In some realities
In existing, sharing feature can be used and carry out multi-class targets detection.Target object for example may include the three classes such as vehicle, animal, people
Target.When target object is animal (such as vagrant dog, strong dog etc.), body characteristics for example can include but is not limited to move
Tooth, tail, eyes of object etc..Body characteristics information can be used to judge the risk of animal.When target object is people,
Body characteristics for example can include but is not limited to face, trunk and four limbs etc..The body characteristics information of people can be used to judge
It is no to there is a possibility that fraud, it is described about this point below in connection with Fig. 4.
Further, analysis ambient image information can also include determining that target object arrival is corresponding by multiple image
The time of wearable device.For example, can judge target object with a distance from wearable device, target pair by multiple image
The direction of motion, movement velocity of elephant etc., to calculate arrival time.Distance, direction and speed can be calculated using various ways
Degree.In one implementation, distance can be big by the size of the size of comparison target object in the picture and actual object
It is small to be estimated.The direction of motion can for example be estimated according to the offset of target object in the picture.Art technology
If personnel are appreciated that the direction of motion of target object does not have user oriented, it is less likely to be present danger.
In some implementations, analysis ambient image information includes analyzing the image from other wearable devices.For example, the
One wearable device and the second wearable device have matched and have shared image information between.In this example, first
Wearable device can analyze the ambient image information from the second wearable device, calculates target object and wearable sets to second
The standby time, then according to the mutual alignment relation between the first and second wearable devices, to determine target object to first
The time of wearable device.In another example, the second wearable device can be wearable to second by the target object of calculating
The time of equipment shares to the first wearable device, to save transmitted data amount, improves treatment effeciency.
In step 302, analysis environmental audio information from wherein acquisition to be possible to jeopardize the information of user security.Equally
Ground, environmental audio information both may include the audio-frequency information of wearable device itself capture, also may include that other wearable set
The audio-frequency information of standby capture.
Specifically, analysis environmental audio information may include extracting the audio spy of target object from environmental audio information
Sign.In some implementations, it can be decomposed according to voice signal base band and reconfiguration technique isolates interested sound from background sound
Sound, such as vehicle, animal or the sound of people.When target object is vehicle, audio frequency characteristics for example be can include but is not limited to
Whistle frequency of vehicle etc..When target object be animal when, audio frequency characteristics for example can include but is not limited to loudness, tone and
Mel frequency cepstral coefficient MFCC etc..When target object is people, audio frequency characteristics for example can include but is not limited to mankind's language
Regular cepstrum coefficient PNCC of sound, speech energy etc..
Then, in step 303, the danger classes of target object is assessed based on the analysis to image, audio-frequency information.Tool
For body, time and the target object of corresponding wearable device are reached according to the body characteristics of target object, target object
Audio frequency characteristics, to assess the danger classes of target object.
In one implementation, when target object is vehicle, the ring of the time, vehicle of user at one's side can be reached to vehicle
Flute frequency is weighted and discretization, to obtain a danger classes, namely the threat level to user.
It in another implementation, can be special according to the body characteristics of animal, audio or sound when target object is animal
Sign to assess animal shape threat degree, such as may include animal angry degree and animal it is strong.Meanwhile it can basis
The time that animal reaches user may attack the probability of user to assess animal.Finally, can add to this two results
Power and discretization, to provide animal threat level namely danger classes.
In another is realized, when target object is people, the danger classes for assessing target object may include that assessment should
Target object is with the presence or absence of potential fraud possibility, as in conjunction with will be described in Fig. 4.
Optionally, in step 304, some additive factors can also be based further on to adjust assessed danger etc.
Grade, to further provide for accurate early warning.
In one implementation, danger classes can be adjusted based on Weather information and/or odiferous information.As previously mentioned
, weather conditions can be sensed by the humidity sensor in the environment information acquisition unit of wearable device.Optionally, may be used
To directly acquire weather forecast by network by the network communication unit of wearable device.Still optionally further, it can be passed through
The sensor of his type senses weather conditions, such as temperature sensor sensing temperature, sound transducer sense thunder, the patter of rain,
Sound of the wind etc., imaging sensor are sensed such as sleet, fine day, cloudy day, lightning.Odiferous information can be felt by smell sensor
It surveys.It is appreciated that the danger classes on rainy day is higher than the danger classes of fine day for example for the danger from vehicle, because
It can be slided for rainy day road surface, it is seen that degree is not high, these factors will lead to driver or user makes a fault, so that traffic thing occur
Therefore.
In another implementation, danger etc. can be adjusted based on the biological information of the wearer (user) of wearable device
Grade.As previously mentioned, the biological information of user can react the physiological status and/or the state of mind of user.When physiological status and/or
When the state of mind is poor, user is easier to come to harm, such as be easier to be deceived, therefore danger can be correspondingly improved etc.
Grade.
With further reference to Fig. 4, it illustrates the flow charts of an exemplary realization of the method and step 303 of Fig. 3, namely show
Go out when target object is people, how to have determined the danger classes of the target object.In this embodiment, the danger of target object
Grade mainly considers target object with the presence or absence of fraud possibility.
As shown in figure 4, in step 401, whether identification target object is stranger.It is appreciated that in most cases,
Danger is from stranger, and therefore, this embodiment is detected mainly for the fraud of stranger.Stranger's identification can be with
The ambient image information and/or environmental audio information obtained based on wearable device.
It in one implementation, can be according to ambient image information to determine whether being stranger.For example, wearable device
Processing unit can carry out Face datection for ambient image information.A variety of face recognition technologies can be taken to carry out face inspection
It surveys.In one implementation, it can be detected according to Adaboost machine learning algorithm, and using Haar feature.It then, can be with
Judge whether the face detected is stranger by retrieval acquaintance database.It can be stored in advance in acquaintance database useful
The face image data of the acquaintance at family.
It in another implementation, can be according to environmental audio information to determine whether being stranger.For example, wearable device
Processing unit can for environmental audio information carry out speech recognition.Multiple voice identification technology can be taken to carry out voice
Detection.In one implementation, it can use sound groove recognition technology in e to identify target object.It then, can be by retrieving acquaintance's number
Judge whether the voice detected belongs to acquaintance or people trusty according to library.User can be previously stored in acquaintance database
Acquaintance voice data and/or voice characteristics data.
It is appreciated that above two realization can carry out any combination.For example, in one implementation, only when two kinds of sides
When formula is all judged as acquaintance, just think that target object is acquaintance.In another implementation, as long as any mode is judged as ripe
People, it can think that target object is acquaintance.
Further, it can also judge whether the personnel detected are to interact with user according to ambient image information
People, namely whether engage in the dialogue with user.In other words, according to body characteristics judge target object whether and user session.?
In a kind of realization, first according to face size judge target object to user distance, for example whether within a predetermined range；Then
Judge whether target object faces user according to human face posture；Finally judge the lip of target object whether dynamic.If this three
It plants while setting up, then it is assumed that target object is exactly the people with user session.In general, stranger's fraud need by pair
Words are to realize.Therefore, in some implementations, the stranger not talked with can be excluded.This judgment step can be examined in face
Survey and sound detection before, later or between, the application in this regard there is no limit.
If judging in step 401, target object for stranger, in step 402, determines the fraud of the target object
Likelihood score, that is, the probability that the target object cheats user.
Fraud likelihood score aspect can judge based on one or more, including but not limited to the language of target object, table
Feelings, movement etc..
In one implementation, the voice content of target object is analyzed based on fraud reference model, cheats likelihood to determine
Degree.Fraud reference model can for example be generated by learning existing fraud case.For example, can be collected from network various
Case is cheated, then learns to cheat language model out using Bayes classifier, as fraud reference model.
In this implementation, the processing unit that can use wearable device is analyzed for environmental audio information.For example,
The regular cepstrum coefficient PNCC feature of speech energy for extracting target object first, then carries out speech recognition, is based on Markov
Random field is segmented and is extracted sensitive vocabulary, and the prediction of deception likelihood score is finally carried out using fraud reference model.Citing
For, when target object says " you is asked to make a call to 100,000 yuans on this bank card ", then the sensitive vocabulary extracted is " bank card "
" money ".By Bayes' theorem it can be concluded that, cheating probability P (deception | " bank card ", " money ")=P (" bank card ", " money " | take advantage of
Deceive) * P (deception)/P (" bank card ", " money "), wherein P (" bank card ", " money " | deception) is indicated in all deception cases, " silver-colored
The probability that row card " and " money " keyword occur simultaneously, P (deception) is prior probability, and P (" bank card ", " money ") is to go out simultaneously
The prior probability of existing keyword " bank card " and " money ".These three probability can be calculated by study fraud language model
Come.
It in another implementation, can be based on the variation of the facial characteristics of target object namely expression, to estimate to cheat likelihood
Degree.In this implementation, the processing unit that can use wearable device analyzes the face of target object for ambient image information
Portion's changing features.According to psychology and/or behavior analysis, certain specific facial characteristics variations be might imply that in corresponding
Be indecisive and changeable dynamic, such as tell a lie etc..Likelihood ratio can be cheated accordingly for these specific facial characteristics variations or combinations thereof distribution,
Such as it is distributed based on psychology and/or behavior theory, and/or corresponding fraud is adjusted based on fraud case statistical analysis
Likelihood ratio.Specific facial characteristics variation for example can include but is not limited to eyeball relative displacement, and eyebrow shape is opposite to be changed, face
Portion's color change etc..The template of facial characteristics variation with deception likelihood score can be constructed.In one implementation, which can be
Each data of one look-up table, look-up table is made of search terms and fraud likelihood ratio.Such as a search terms can be defined
Are as follows: eyeball moves right, eyebrow to raise up, face reddens slightly, corresponding likelihood probability of cheating is 0.7.
In another is realized, it can be changed based on the behavior act of target object to estimate to cheat likelihood score.It is real herein
In existing, the processing unit that equally can use wearable device analyzes the behavior act of target object for ambient image information
Variation.According to psychology and/or behavior analysis, certain specific behavior act variations might imply that is indecisive and changeable in corresponding
It is dynamic, such as tell a lie etc..Likelihood ratio can be cheated accordingly for these specific behavior act variations or combinations thereof distribution, such as
It is distributed based on psychology and/or behavior theory, and/or adjusts corresponding fraud likelihood based on fraud case statistical analysis
Rate.Specific behavior act variation is acted such as can include but is not limited to hand and touch neck, shrug.Behavior act can be constructed
The template of variation and deception likelihood ratio.The detection of movement variation can take various ways.Such as colour of skin mould can be used first
Type carries out the detection of hand, detects shoulder using skeleton analysis, is then carried out using TLD (tracking-study-detection) track algorithm
The tracking of hand, shoulder finally carries out the prediction of fraud likelihood score to obtain the track sets of hand, shoulder based on track sets.
For example, when detect it is in one's hands touch neck, then hand deception likelihood ratio is P (deception | hand touches neck), and detects and shrug
When, shoulder deception likelihood ratio is P (deception | shrug), and integrated deception likelihood score can be with are as follows: and P (deception | hand touches neck, shrugs)=P
(deception | hand touches neck)+P (deception | shrug)-P (deception | hand touches neck) P (deception | shrug).
It is appreciated that above-mentioned three kinds of realizations can carry out any combination.For example, in one implementation, can calculate separately
Three kinds are realized identified fraud likelihood score, and the fraud likelihood score total with determination is then weighted to three.
Continue Fig. 4, finally in step 403, based on estimated fraud likelihood score come assigning degrees of hazard.
In general, the fraud likelihood score of estimation can be indicated with numerical value such as percentages.Fraud likelihood score can be mapped to
Corresponding danger classes, in order to provide corresponding warning information according to danger classes subsequent.
Fig. 4 description above mentioned embodiment provide a kind of detection methods of the potential fraud of stranger.This scheme
The range for expanding and can detect danger is provided, the safety coefficient for improving user is conducive to.
It should be noted that although describing the operation of the method for the present invention in the accompanying drawings with particular order, this is not required that
Or hint must execute these operations in this particular order, or have to carry out operation shown in whole and be just able to achieve the phase
The result of prestige.On the contrary, the step of describing in flow chart can change and execute sequence.In some embodiments, the step in Fig. 3
302 can carry out before step 301, and the two can also carry out simultaneously.Additionally or alternatively, it is convenient to omit certain steps,
Multiple steps are merged into a step to execute, and/or a step is decomposed into execution of multiple steps.
Fig. 5 shows the structural representation of the risk early warning device based on wearable device according to embodiments herein
Figure.
As shown in figure 5, risk early warning device 500 includes receiving unit 510, hazard event determination unit 520 and alarm signal
Breath provides unit 530.Receiving unit 510 is configured to receive the ambient condition information obtained via the first wearable device, ring
Border information includes ambient image information and environmental audio information.Hazard event determination unit 520 is configured to based on receiving unit
The 510 received environmental informations of institute, it is determined whether dangerous event.Warning information provides unit 530 and is configured in response to true
Fixed dangerous event, provides warning information.
In some embodiments, receiving unit 510 can also be configured to receive via the acquisition of the second wearable device
Information, the information may include at least one of following: the biological information of the wearer of the second wearable device, environmental information, with
And second wearable device generate information.In this embodiment, hazard event determination unit 520 may be configured to also be based on
The information determines whether there is hazard event.
In some embodiments, hazard event determination unit 520 may include image analysis subelement 521, audio analysis
Subelement 522 and threat level assessment subelement 523.
Image analysis subelement 521 may be configured to the body characteristics based on ambient image information detected target object simultaneously
Determine that target object reaches the time of corresponding wearable device.Audio analysis subelement 522 may be configured to based on environment
The audio frequency characteristics of audio information target object.Threat level assessment subelement 523 may be configured to according to target object
Body characteristics, target object reach the time of corresponding wearable device and the audio frequency characteristics of target object, assess target
The danger classes of object.
In one implementation, target object is vehicle, and the audio frequency characteristics of target object include the whistle frequency of vehicle.
In another implementation, target object is animal, the body characteristics of target object include the tooth of animal, tail and
In eyes at least one of, the audio frequency characteristics of target object include in loudness, tone and Mel frequency cepstral coefficient MFCC at least
One.
In another is realized, target object is behaved, the body characteristics of target object include face, trunk, in four limbs extremely
One item missing, the audio frequency characteristics of target object include human speech, the regular cepstrum coefficient PNCC of speech energy.
In some embodiments, environmental information further includes Weather information and/or odiferous information.In these embodiments, it connects
At least one of reception or less can also be configured to by receiving unit 510: the weather conditions sensed via sensor；And via network
Received weather forecast.At this point, hazard event determination unit 520 can also include: danger classes adjustment subelement 524, configuration
For adjusting danger classes based on Weather information and/or odiferous information.
In some embodiments, receiving unit 510 can also be configured to receive via the acquisition of the first wearable device
The biological information of the wearer of first wearable device.In these embodiments, hazard event determination unit 520 can also wrap
Include: danger classes adjusts subelement 524, is configured to adjust danger classes based on biological information.
In some embodiments, warning information provides unit 530 and is further configured to obtain the first wearable device
The feedback information of wearer；And warning information is provided based on feedback information.
In further embodiments, warning information provides unit 530 and is further configured to based on danger classes offer pair
Answer the warning information of grade.
In some embodiments, receiving unit 510 is also configured to receive first obtained via the first wearable device
The biological information of the wearer of wearable device.In these embodiments, warning information provides unit 530 and can further configure
The mode of warning information is provided for adjusting based on biological information.
It should be appreciated that in the method that all units or module recorded in risk early warning device 500 and reference Fig. 2-3 are described
Each step is corresponding.As a result, above with respect to method description operation and feature be equally applicable to risk early warning device 500 and its
In include unit, details are not described herein.
Fig. 6 shows a kind of exemplary realization of the threat level assessment subelement 523 in Fig. 5, which uses
In the detection method for implementing the potential fraud of stranger described in Fig. 4.As shown in fig. 6, threat level assessment subelement 523
It may include stranger's identification module 601, fraud likelihood score determining module 602 and danger classes determining module 603.
Stranger's identification module 601 may be configured to whether identification target object is stranger.For example, can be according to people
Face feature and/or phonetic feature judged.Fraud likelihood score determining module 602 may be configured to determine stranger
Fraud likelihood score.Fraud likelihood score can for example be estimated based on the language of stranger, expression, movement etc..Danger etc.
Grade determining module 603 may be configured to based on estimated fraud likelihood score come assigning degrees of hazard.
It should be appreciated that all units or module recorded in threat level assessment subelement 523 and the method with reference to Fig. 4 description
In each step it is corresponding.The operation above with respect to method description and feature are equally applicable to threat level assessment as a result,
Unit 523 and unit wherein included, details are not described herein.
As previously mentioned, wearable device provided by the present application can also include third party's assist in functions.For example, figure
Wearable device 100 shown in 1 can also include transmission unit 140.Transmission unit 140 may be configured to receive from it
The information of his wearable device (such as wearable device of user 40).Transmission unit 140 also may be configured to send and can wear
Wear the information of equipment 100.The information of transmission can include but is not limited to the biological information of the wearer of wearable device, environment letter
The information that breath and wearable device generate, such as the hazard event determination unit danger classes letter generated of wearable device
Breath.
Therefore, present invention also provides a kind of information sharing methods based on wearable device.In one implementation, the party
Method for example may include: that the biological information of user is obtained via the wearable device of user；Meet in response to the biological information pre-
Fixed condition, it is shared to other one or more wearable device solicited messages；And based on being obtained via the wearable device of user
The environmental information of surrounding and the information that other one or more wearable devices are shared are taken, target object is searched for.Pass through letter
Sharing mode is ceased, can be provided for user from third-party early warning, to increase safety coefficient.
Fig. 7 shows an exemplary scene of the danger early warning method provided by the present application based on wearable device,
That is an exemplary scene of above- mentioned information sharing method.In this scene, the companion (such as little girl) of user is in the street
It is lost.When user is very anxious, the wearable device of the invention that user is worn is sensed by biometric information sensor
Periphery other users are communicated to the anxiety psychology of user, and by this anxious psychology.Other users perceive the tired of the user
Border can open Image Sharing function, so that the visual field of the user is extended, so that the little girl to wander away is more easily found.
As shown in fig. 7, user has found that companion (little girl) loses in frame 701.Then, in block 702, the user
Wearable device (the first wearable device) can sense the physiological status of user by biometric information sensor.When detecting use
When the anxiety psychology at family, the first wearable device can be total to neighbouring one or more the second wearable device solicited message
It enjoys.For example, the first wearable device can be set by the server of early warning system to neighbouring one or more second is wearable
Preparation is delivered letters breath sharing request.In another example the first wearable device can direct broadcast message sharing request, for neighbouring by the
The detection of two wearable devices.
In frame 703, neighbouring other users (the second wearable device) receive information sharing request.Then, in frame
In 704, these the second wearable device opening imformation sharing functionalities are to provide help.
In frame 706, the second wearable device can be by the image in its visual field, optionally further comprising audio-frequency information, uploads
To cloud database, to be shared with the first wearable device.In addition, as shown in frame 707, these second wearable devices can be with
Its geographical location information is provided, such as determines its position by GPS module.
At the same time, in frame 705, the first wearable device also its available ambient enviroment image to be searched.
Then, in frame 708, based on the information that the first wearable device itself obtains, and one or more second can
Wearable device shared information searches target.For example, image information can be based on, also looked for according to body or aspectual character small
Girl.
Finally, due to being expanded by the visual field of information sharing mode, user, can quickly be found in frame 709
Little girl.
In some implementations, the function of being searched by image procossing can execute at the server of early warning system.
In this way, the processing work of the first wearable device can be mitigated.In other realizations, the function searched by image procossing
It can be distributed at each wearable device and execute, processing can be further speeded up in this way.
It can be real by way of software it should be noted that being described in unit module involved in the embodiment of the present application
It is existing, it can also be realized by way of hardware.Described unit module also can be set in processor (for example, the place of Fig. 1
Manage unit 120) in, for example, can be described as: a kind of processor includes receiving unit, hazard event determination unit and alarm signal
Breath provides unit.Wherein, the title of these unit modules does not constitute the restriction to the unit module itself under certain conditions,
For example, receiving unit is also described as " for receiving the list of the ambient condition information obtained via the first wearable device
Member ".
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (42)
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410638409.6A CN105632049B (en) | 2014-11-06 | 2014-11-06 | A kind of early warning method and device based on wearable device |
| KR1020150137084A KR102408257B1 (en) | 2014-11-06 | 2015-09-25 | The method and apparatus for early warning the danger |
| EP15857475.6A EP3217370A4 (en) | 2014-11-06 | 2015-10-20 | Method and apparatus for early warning of danger |
| US15/525,218 US10121075B2 (en) | 2014-11-06 | 2015-10-20 | Method and apparatus for early warning of danger |
| PCT/KR2015/011083 WO2016072644A1 (en) | 2014-11-06 | 2015-10-20 | Method and apparatus for early warning of danger |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410638409.6A CN105632049B (en) | 2014-11-06 | 2014-11-06 | A kind of early warning method and device based on wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105632049A CN105632049A (en) | 2016-06-01 |
| CN105632049B true CN105632049B (en) | 2019-06-14 |
Family
ID=56046924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410638409.6A Active CN105632049B (en) | 2014-11-06 | 2014-11-06 | A kind of early warning method and device based on wearable device |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US10121075B2 (en) |
| EP (1) | EP3217370A4 (en) |
| KR (1) | KR102408257B1 (en) |
| CN (1) | CN105632049B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555987A (en) * | 2019-08-01 | 2019-12-10 | 宝能汽车有限公司 | wisdom wearing equipment |
Families Citing this family (66)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9500865B2 (en) * | 2013-03-04 | 2016-11-22 | Alex C. Chen | Method and apparatus for recognizing behavior and providing information |
| CN105632049B (en) * | 2014-11-06 | 2019-06-14 | 北京三星通信技术研究有限公司 | A kind of early warning method and device based on wearable device |
| JP6605442B2 (en) * | 2016-12-27 | 2019-11-13 | 本田技研工業株式会社 | Information providing apparatus and information providing method |
| WO2018124584A1 (en) * | 2016-12-28 | 2018-07-05 | 삼성전자 주식회사 | Personal safety device and operating method therefor |
| US10567642B2 (en) | 2017-02-24 | 2020-02-18 | International Business Machines Corporation | Managing camera usage with warnings and/or disablement |
| CN107491642B (en) * | 2017-08-17 | 2021-08-31 | 深圳先进技术研究院 | User's security protection method, device, device and storage medium |
| CN107729737B (en) * | 2017-11-08 | 2020-07-03 | 广东小天才科技有限公司 | A method for acquiring identity information and a wearable device |
| CN108169761B (en) * | 2018-01-18 | 2024-08-06 | 上海瀚莅电子科技有限公司 | Fire scene task determination method, device and system and computer readable storage medium |
| JP7095312B2 (en) * | 2018-03-01 | 2022-07-05 | オムロン株式会社 | Hazard level detection device, risk level detection method, and risk level detection program |
| CN108364440A (en) * | 2018-03-12 | 2018-08-03 | 深圳市沃特沃德股份有限公司 | Remind method and device of the children far from button in automobile |
| JP7225551B2 (en) * | 2018-03-23 | 2023-02-21 | 富士フイルムビジネスイノベーション株式会社 | Biting detection device and program |
| KR102419007B1 (en) | 2018-04-10 | 2022-07-08 | 한국전자통신연구원 | Apparatus for warning dangerous situation and method for the same |
| CN108922138A (en) * | 2018-06-22 | 2018-11-30 | 张小勇 | A kind of data processing method and system |
| CN108777055A (en) * | 2018-06-26 | 2018-11-09 | 上海理工大学 | A kind of multifunctional infant safety guard |
| US10607367B2 (en) | 2018-06-26 | 2020-03-31 | International Business Machines Corporation | Methods and systems for managing virtual reality sessions |
| CN110795971B (en) * | 2018-08-02 | 2023-02-17 | 深圳云天励飞技术有限公司 | User behavior identification method, device, equipment and computer storage medium |
| CN109151719B (en) * | 2018-09-28 | 2021-08-17 | 北京小米移动软件有限公司 | Secure boot method, device and storage medium |
| KR102699141B1 (en) * | 2018-10-12 | 2024-08-28 | 현대자동차주식회사 | Vehicle and method for outputting information |
| US10679602B2 (en) * | 2018-10-26 | 2020-06-09 | Facebook Technologies, Llc | Adaptive ANC based on environmental triggers |
| CN110197569B (en) * | 2018-11-19 | 2021-06-25 | 广东小天才科技有限公司 | A wearable device-based security monitoring method and wearable device |
| CN109472963B (en) * | 2018-11-29 | 2020-12-01 | 山西凯普勒科技有限公司 | a smart bracelet |
| CN109658666A (en) * | 2018-12-06 | 2019-04-19 | 中山乐心电子有限公司 | Danger protection method, equipment, system, electronic equipment and storage medium |
| CN109684989A (en) * | 2018-12-20 | 2019-04-26 | Oppo广东移动通信有限公司 | safety monitoring method, device, terminal and computer readable storage medium |
| CN109639906A (en) * | 2019-01-25 | 2019-04-16 | 维沃移动通信有限公司 | A kind of method for early warning and mobile terminal |
| US11076274B1 (en) * | 2019-01-28 | 2021-07-27 | United Services Automobile Association (Usaa) | Monitoring of data to predict driving events |
| CN110175593A (en) * | 2019-05-31 | 2019-08-27 | 努比亚技术有限公司 | Suspect object processing method, wearable device and computer readable storage medium |
| JP7462386B2 (en) * | 2019-06-14 | 2024-04-05 | 株式会社シマノ | DETECTION APPARATUS, DETECTION METHOD, GENERATION METHOD, COMPUTER PROGRAM, AND STORAGE MEDIUM |
| CN110414390A (en) * | 2019-07-13 | 2019-11-05 | 恒大智慧科技有限公司 | Canine recognition methods, system and readable storage medium storing program for executing in a kind of community |
| CN112419661A (en) * | 2019-08-20 | 2021-02-26 | 北京国双科技有限公司 | Danger identification method and device |
| JP7296626B2 (en) * | 2019-08-26 | 2023-06-23 | 株式会社Agama-X | Information processing device and program |
| CN112561113B (en) * | 2019-09-25 | 2025-02-14 | 华为技术有限公司 | Dangerous scene warning method and terminal equipment |
| CN110807895A (en) * | 2019-10-14 | 2020-02-18 | 珠海市魅族科技有限公司 | Monitoring method, device, equipment and storage medium based on intelligent wearable equipment |
| KR102250498B1 (en) * | 2019-11-07 | 2021-05-11 | 한양대학교 산학협력단 | Architecture and electronc device implementing the architecture for safety and survivability wearable system based on artificial intelligence and internet of things, and operating method thereof |
| CN111009105B (en) * | 2019-12-28 | 2022-03-08 | 杭州好育信息科技有限公司 | Communication method and system based on intelligent wearable device |
| CN111179542A (en) * | 2020-01-03 | 2020-05-19 | 甄十信息科技（上海）有限公司 | Intelligent watch and safety monitoring method thereof |
| CN111479127A (en) * | 2020-02-27 | 2020-07-31 | 视联动力信息技术股份有限公司 | Data processing method, device and computer readable storage medium |
| CN111833575A (en) * | 2020-07-15 | 2020-10-27 | 徐州炫云信息科技有限公司 | Bluetooth type prevention and control system for medical risk prevention and control |
| US12251991B2 (en) | 2020-08-20 | 2025-03-18 | Denso International America, Inc. | Humidity control for olfaction sensors |
| US11636870B2 (en) | 2020-08-20 | 2023-04-25 | Denso International America, Inc. | Smoking cessation systems and methods |
| US11760170B2 (en) | 2020-08-20 | 2023-09-19 | Denso International America, Inc. | Olfaction sensor preservation systems and methods |
| US12017506B2 (en) | 2020-08-20 | 2024-06-25 | Denso International America, Inc. | Passenger cabin air control systems and methods |
| US12377711B2 (en) | 2020-08-20 | 2025-08-05 | Denso International America, Inc. | Vehicle feature control systems and methods based on smoking |
| US11932080B2 (en) | 2020-08-20 | 2024-03-19 | Denso International America, Inc. | Diagnostic and recirculation control systems and methods |
| US11881093B2 (en) | 2020-08-20 | 2024-01-23 | Denso International America, Inc. | Systems and methods for identifying smoking in vehicles |
| US11760169B2 (en) | 2020-08-20 | 2023-09-19 | Denso International America, Inc. | Particulate control systems and methods for olfaction sensors |
| US11813926B2 (en) | 2020-08-20 | 2023-11-14 | Denso International America, Inc. | Binding agent and olfaction sensor |
| US12269315B2 (en) | 2020-08-20 | 2025-04-08 | Denso International America, Inc. | Systems and methods for measuring and managing odor brought into rental vehicles |
| US11828210B2 (en) | 2020-08-20 | 2023-11-28 | Denso International America, Inc. | Diagnostic systems and methods of vehicles using olfaction |
| CN112738471A (en) * | 2020-12-28 | 2021-04-30 | 詹晨 | Security monitoring data processing method based on Internet of things and artificial intelligence and cloud communication server |
| KR102538688B1 (en) | 2021-01-14 | 2023-05-30 | (주)세이프티온솔루션 | Risk assessment based accident predction safety management device and method |
| US11961392B2 (en) * | 2021-03-04 | 2024-04-16 | The University Of North Carolina At Charlotte | Worker-in-the-loop real time safety system for short-duration highway workzones |
| CN113099178B (en) * | 2021-04-01 | 2021-12-03 | 广州市宁葳信息科技有限公司 | Intelligent community safety online real-time monitoring and early warning method based on video remote monitoring |
| US12050261B2 (en) * | 2021-05-12 | 2024-07-30 | California State University Fresno Foundation | System and method for human and animal detection in low visibility |
| CN115482645A (en) * | 2021-05-31 | 2022-12-16 | 漳州立达信光电子科技有限公司 | Method and device for detecting dangerous incidents involving objects |
| EP4130936A1 (en) * | 2021-08-02 | 2023-02-08 | BAE SYSTEMS plc | Positioning apparatus and method |
| CN113470313B (en) * | 2021-09-02 | 2021-11-19 | 广州乐盈信息科技股份有限公司 | Emergency alarm system based on cloud pipe end |
| KR102386208B1 (en) * | 2022-01-03 | 2022-04-15 | 주식회사 서플라이스 | Method and apparatus for detecting hazardous situations in fiteness center using neural network model |
| CN114821738A (en) * | 2022-05-13 | 2022-07-29 | 睿云奇智(青岛)科技有限公司 | Safety early warning method and device, computer equipment and readable storage medium |
| CN115002598B (en) * | 2022-05-26 | 2024-02-13 | 歌尔股份有限公司 | Headset mode control method, headset device, head-mounted device and storage medium |
| CN115049987B (en) | 2022-08-12 | 2022-11-04 | 星宠王国(北京)科技有限公司 | Pet safety management method, system, computer equipment and storage medium |
| CN115790569A (en) * | 2022-11-14 | 2023-03-14 | 歌尔科技有限公司 | Head-mounted display device and navigation method for assisting navigation |
| CN116249228A (en) * | 2022-12-09 | 2023-06-09 | 深圳曲速空间科技有限公司 | Auxiliary method, device and electronic equipment for reducing information packet loss in wireless data transmission |
| WO2024177289A1 (en) * | 2023-02-20 | 2024-08-29 | 삼성전자주식회사 | Wearable device for placing virtual object corresponding to external object in virtual space, and method therefor |
| US12299557B1 (en) | 2023-12-22 | 2025-05-13 | GovernmentGPT Inc. | Response plan modification through artificial intelligence applied to ambient data communicated to an incident commander |
| US12392583B2 (en) | 2023-12-22 | 2025-08-19 | John Bridge | Body safety device with visual sensing and haptic response using artificial intelligence |
| CN118692031B (en) * | 2024-08-26 | 2024-11-19 | 苏州奥特兰恩自动化设备有限公司 | Potential danger identification system based on environment perception |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101108125A (en) * | 2007-08-02 | 2008-01-23 | 张志强 | Dynamic monitoring system of body sign |
| CN101714208A (en) * | 2008-09-29 | 2010-05-26 | 富士胶片株式会社 | Portable suspicious individual detection apparatus, suspicious individual detection method, and computer-readable medium |
| CN103106374A (en) * | 2013-01-15 | 2013-05-15 | 广东欧珀移动通信有限公司 | Safety pre-warning processing method, system and mobile terminal of reminding user of mobile terminal |
| CN103325210A (en) * | 2012-03-23 | 2013-09-25 | 索尼公司 | Modularized mobile health and security system |
| CN203872286U (en) * | 2014-05-26 | 2014-10-08 | 北京中电兴发科技有限公司 | Intelligent monitoring device |
Family Cites Families (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9929745D0 (en) * | 1999-12-17 | 2000-02-09 | Secr Defence | Determining the efficiency of respirators and protective clothing and other improvements |
| JP3979351B2 (en) * | 2003-06-30 | 2007-09-19 | ソニー株式会社 | Communication apparatus and communication method |
| US7921036B1 (en) | 2002-04-30 | 2011-04-05 | Videomining Corporation | Method and system for dynamically targeting content based on automatic demographics and behavior analysis |
| KR20060095556A (en) | 2003-09-30 | 2006-08-31 | 코닌클리케 필립스 일렉트로닉스 엔.브이. | Use content identifiers to download CD-cover pictures to represent audio content items |
| JP2007221328A (en) * | 2006-02-15 | 2007-08-30 | Sony Corp | Command system, imaging device, command device, imaging processing method, command processing method, program |
| US8928752B2 (en) * | 2006-08-31 | 2015-01-06 | Stellar Llc | Recording device with pre-start signal storage capability |
| JP2009010831A (en) | 2007-06-29 | 2009-01-15 | Toshiba Corp | Image analyzer and image analysis method |
| US9107012B2 (en) | 2011-12-01 | 2015-08-11 | Elwha Llc | Vehicular threat detection based on audio signals |
| US9368028B2 (en) * | 2011-12-01 | 2016-06-14 | Microsoft Technology Licensing, Llc | Determining threats based on information from road-based devices in a transportation-related context |
| JP2013171476A (en) | 2012-02-22 | 2013-09-02 | Nec Corp | Portable back camera system for face recognition crime prevention and crime prevention determination method used for the same |
| KR101375868B1 (en) * | 2012-08-07 | 2014-03-17 | 한양대학교 산학협력단 | Wearable Display Deice Having Sensing Function |
| KR101321157B1 (en) * | 2012-08-07 | 2013-10-23 | 한양대학교 산학협력단 | Wearable display deice having sliding structure |
| US9568735B2 (en) * | 2012-08-07 | 2017-02-14 | Industry-University Cooperation Foundation Hanyang University | Wearable display device having a detection function |
| US9465216B2 (en) * | 2012-08-07 | 2016-10-11 | Industry-University Cooperation Foundation Hanyang University | Wearable display device |
| KR20140024712A (en) | 2012-08-21 | 2014-03-03 | 홍순선 | User location based monitoring service providing method for user surroundings image using smart device |
| TWI486915B (en) * | 2012-10-25 | 2015-06-01 | Hon Hai Prec Ind Co Ltd | Personal protective equipment, danger early-waning system and method |
| JP2015041969A (en) * | 2013-08-23 | 2015-03-02 | ソニー株式会社 | Image acquisition apparatus, image acquisition method, and information distribution system |
| KR101395614B1 (en) | 2013-12-06 | 2014-05-16 | 조원석 | Device for pulse-measuring and image-recording and transmitting using smart-watch |
| US9360682B1 (en) * | 2014-05-07 | 2016-06-07 | Remote Xccess, LLC | Camera headband device and system with attachable apparatus |
| US20160112636A1 (en) * | 2014-10-20 | 2016-04-21 | Panasonic Intellectual Property Management Co., Ltd. | Wearable camera |
| CN105632049B (en) * | 2014-11-06 | 2019-06-14 | 北京三星通信技术研究有限公司 | A kind of early warning method and device based on wearable device |
| GB2536215B (en) * | 2015-03-05 | 2018-01-31 | Samsung Electronics Co Ltd | Secure input mode for user device |
| WO2017120541A1 (en) * | 2016-01-06 | 2017-07-13 | Advanced Wireless Innovations Llc | Wireless security system |
| US10102732B2 (en) * | 2016-06-28 | 2018-10-16 | Infinite Designs, LLC | Danger monitoring system |
| US9934658B1 (en) * | 2016-09-14 | 2018-04-03 | Siemens Industry, Inc. | Visually-impaired-accessible building safety system |
-
2014
- 2014-11-06 CN CN201410638409.6A patent/CN105632049B/en active Active
-
2015
- 2015-09-25 KR KR1020150137084A patent/KR102408257B1/en active Active
- 2015-10-20 EP EP15857475.6A patent/EP3217370A4/en not_active Withdrawn
- 2015-10-20 US US15/525,218 patent/US10121075B2/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101108125A (en) * | 2007-08-02 | 2008-01-23 | 张志强 | Dynamic monitoring system of body sign |
| CN101714208A (en) * | 2008-09-29 | 2010-05-26 | 富士胶片株式会社 | Portable suspicious individual detection apparatus, suspicious individual detection method, and computer-readable medium |
| CN103325210A (en) * | 2012-03-23 | 2013-09-25 | 索尼公司 | Modularized mobile health and security system |
| CN103106374A (en) * | 2013-01-15 | 2013-05-15 | 广东欧珀移动通信有限公司 | Safety pre-warning processing method, system and mobile terminal of reminding user of mobile terminal |
| CN203872286U (en) * | 2014-05-26 | 2014-10-08 | 北京中电兴发科技有限公司 | Intelligent monitoring device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555987A (en) * | 2019-08-01 | 2019-12-10 | 宝能汽车有限公司 | wisdom wearing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| EP3217370A1 (en) | 2017-09-13 |
| CN105632049A (en) | 2016-06-01 |
| KR102408257B1 (en) | 2022-06-13 |
| EP3217370A4 (en) | 2018-01-17 |
| US20170323161A1 (en) | 2017-11-09 |
| US10121075B2 (en) | 2018-11-06 |
| KR20160054397A (en) | 2016-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105632049B (en) | A kind of early warning method and device based on wearable device | |
| US8442832B2 (en) | Apparatus for context awareness and method using the same | |
| Mubashir et al. | A survey on fall detection: Principles and approaches | |
| Ouchi et al. | Indoor-outdoor activity recognition by a smartphone | |
| Xu et al. | Attention-based gait recognition and walking direction estimation in Wi-Fi networks | |
| CN110677618A (en) | Monitoring method and monitoring system using multi-dimensional sensor data | |
| US20080169929A1 (en) | Warning a user about adverse behaviors of others within an environment based on a 3d captured image stream | |
| CN104468981B (en) | A kind of campus despot based on intelligent mobile phone platform insults detection method | |
| US10867527B2 (en) | Process and wearable device equipped with stereoscopic vision for helping the user | |
| EP2529184A1 (en) | Systems, methods, and apparatuses for providing context-based navigation services | |
| CN109620184A (en) | Mobile phone-wearable device integral type human body burst injury real-time monitoring alarming method | |
| CN113689660A (en) | Safety early warning method of wearable device and wearable device | |
| CN219921037U (en) | Animal sign monitoring device and animal intelligent wearable device | |
| Барковська et al. | Intelligent assistance system for people with visual impairments | |
| Daga et al. | Applications of human activity recognition in different fields: a review | |
| Luthuli et al. | Smart Walk: A Smart Stick for the Visually Impaired | |
| CN118285757A (en) | Wearable health detection bracelet and monitoring system thereof | |
| Saha et al. | Visual, navigation and communication aid for visually impaired person | |
| Prakash et al. | An IoT‐Based Gadget for Visually Impaired People | |
| Botella-Campos et al. | A new system to detect coronavirus social distance violation | |
| KR101862337B1 (en) | Apparatus, method and computer readable recoding medium for offering information | |
| Meghana et al. | Smart system with descriptive video service and spoken dialogue system for visually impaired individuals | |
| CN114821456A (en) | Dangerous event detection method, device, electronic device and storage medium | |
| Pati et al. | Navigating the unseen: Ultrasonic technology for blind navigation | |
| CN113781278B (en) | Event prompting method, device, equipment and storage medium based on feature recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |